© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10081
    Prev
    Next
    INDEX
    Explanations

    Windows programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atsu
    -0.09
    使æĪij
    -0.09
    çŃĩ
    -0.08
    ä¸Ĭ线
    -0.08
    èĦ±èIJ½
    -0.08
    berry
    -0.08
    oti
    -0.08
    etu
    -0.08
    ä»İ严
    -0.08
    illy
    -0.08
    POSITIVE LOGITS
    DWORD
    0.13
     DWORD
    0.11
     Windows
    0.11
    微软
    0.11
     lParam
    0.10
     Microsoft
    0.10
     WINAPI
    0.10
    (hwnd
    0.10
     dword
    0.10
    hwnd
    0.10
    Activations Density 0.734%

    No Known Activations